Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation
Paper
•
2501.17433
•
Published
•
10
•
3
TianshengHuang
TianshengHuang
AI & ML interests
LLM safety
Recent Activity
upvoted
a
paper
23 days ago
AgentReview: Exploring Peer Review Dynamics with LLM Agents
upvoted
a
paper
23 days ago
Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents
upvoted
a
paper
25 days ago
Large Reasoning Models Learn Better Alignment from Flawed Thinking
Organizations
